AI News, BOOK REVIEW: MIT researchers use AI to discover a welcome new antibiotic artificial intelligence

The President's Perspective

This clash leads Radiolab's Latif into a years-long investigation, picking apart evidence, attempting to separate fact from fiction, and trying to uncover what this man actually did or didn't do.

Along the way, Radiolab's Latif reflects on American values and his own religious past, and wonders how his namesake, a fellow nerdy, suburban Muslim kid, may have gone down such a strikingly different path.

Episode 1: My Namesake We hear the evidence against Abdul Latif Nasser — at least the evidence that has been leaked or declassified — and we meet Shelby Sullivan-Bennis, his attorney, who contests more or less every government claim against him.

MIT Research Breakthrough: Deep Learning-driven Antibiotic Drug Discovery Platform

Researcher scientists from Massachusetts Institute of Technology (MIT) used artificial intelligence to identify a new type of antibiotic.

By analyzing over one hundred million chemical compounds in days which can kill 35 types of potentially deadly bacteria, including some strains resistant to all known antibiotics.

The MIT team has created a platform that may offer drug developers the opportunity to utilize the power of AI to lead in a new age of antibiotic drug discovery. Moving forward, the paradigm shifting approach leverages deep learning during the entire antibiotic drug development Lifecyle.

The growing antibiotic resistance, a disturbing trend threatening public health is intensified by two trends including 1) an increasing number of resistant pathogens and 2) a weak antibiotic drug development pipeline in biopharma industry.

coli.  To pull this off, they had to train the model on about 2,500 molecules, including approximately 1,700 FDA-approved drugs and a set of 800 natural products with diverse structures and a wide range of bioactivities. The researchers sufficiently trained the model and then worked with the Broad Institute’s Drug Repurposing Hub, a library of approximately 6,000 compounds.

They applied the model against the thousands of compounds and the model selected one molecule that it calculated to possess superior antibacterial activity in addition to a unique chemical structure—e.g.

It would appear based on the MIT research that the identified molecule disrupts bacteria’ ability to maintain an electrochemical gradient across their cell membranes, reports MIT News. In this way, bacteria cannot produce sufficient molecules to store energy leading to the cells’ death.

This was in stark comparison to ciprofloxacin which in a test the researchers found the bacteria had developed resistance within one to three days—by day 30 the bacteria grew its resistance to ciprofloxacin by 200 times.

Now the research team members will continue leveraging the ZINC15 database, using the model to design new antibiotics and optimizing existing molecules. They will consider advanced optimization schemes, such as training the model to add features that make a particular antibiotic target only select bacteria while ensuring it doesn’t kill beneficial bacterial in a patient’s digestive tract for example.

Scientists at MIT have Discovered a New Antibiotic Using Artificial Intelligence

Using AI technology, a group of researchers at MIT and the Broad Institute have revealed a molecule with the ability to efficiently kill some of the most high-priority pathogens currently threatening human health.

In mice models, Halicin was found to have potent antimicrobial activity against some of the most dangerous resistant infections such as Clostridioides difficile and pan-resistant Acinetobacter baumannii.

This whole process took only 4 days, which is astounding when you consider the largest library able to be manually screened with empirical methods is ten times smaller and can take years.

baumannii which halicin has potential to treat is currently resistant to all known antibiotics and is currently a huge problem among US soldiers deployed in Iraq and Afghanistan.

The bacteria is of little threat to healthy individuals, however, those with weaker immune systems or injuries are significantly more susceptible, leading to higher instances in hospitals.

It is thought that infection rates are high among soldiers due to the multiple instances of exposure to different medical environments that recruits will endure before heading back to their home country following an injury.

The team hopes that in the future, this could lead to the development of treatments that could be delivered intravenously to a precise site of infection, so as not to interfere with the bacteria that live within us harmlessly.

Original Research Paper — A Deep Learning Approach to Antibiotic Discovery Artificial intelligence yields new antibiotic Drug Repurposing Hub Introducing Deep Learning and Neural Networks — Deep Learning for Rookies (1) Explained: Neural networks Trends and Exceptions of Physical Properties on Antibacterial Activity for Gram-Positive and Gram-Negative Pathogens Acinetobacter in modern warfare Epidemiology of Infections Associated With Combat-Related… : Journal of Trauma and Acute Care Surgery ZINC 15 — Ligand Discovery for Everyone

Will Self-Taught, A.I. Powered Robots Be the End of Us?

Success in creating effective A.I.,” said the late Stephen Hawking, “could be the biggest event in the history of our civilization. Or the worst. We just don't know.

MLTalks with Douglas Rushkoff

Team Human: How people, together, can rule the digital future Douglas Rushkoff hosted by Kate Darling Team Human delivers a call to arms. If we are to resist ...

Interview with Ron Weiss: Advances in Synthetic Biology

Hear about the advances in medicine and environmental sustainability that synthetic biology is enabling, and how you can learn more about biological ...

Yuval Noah Harari In Conversation with Christine Lagarde

Christine Lagarde, Managing Director of the International Monetary Fund, hosts Yuval Noah Harari for a conversation about his new book, 21 Lessons for the ...

Algorithmic Justice: Race, Bias, and Big Data

Data are not objective; algorithms have biases; machine learning doesn't produce truth. These realities have uneven effects on people's lives, often serving to ...

HLS Library Book Talk | Cass Sunstein, "How Change Happens"

How does social change happen? When do social movements take off? Sexual harassment was once something that women had to endure; now a movement ...

Next Big Things

In recognition of the promise and progress of creative and collaborative projects underway at HMS, join us for a celebration of the Dean's Innovation and ...

MS&E Reunion 2018: Eric Horvitz—From Decision Analysis to Artificial Intelligence

Eric Horvitz's talk focused on the influence Prof. Howard's teachings had on him, as well as the intersection of artificial intelligence and decision analysis.

MIT Media Lab Space Exploration Initiative: Beyond the Cradle

The public grand opening of Space draws near. Much as biology has witnessed an explosion of DIY bio-hacking in recent years, the dropping costs of space ...